Setup guide intro with a product image: +$0.01 to $0.03 a second
Adding product_image to a Sume avatar video raises the per-second rate by $0.01 on Standard, $0.013 on Plus and $0.03 on Max: +$0.30, $0.39 or $0.90 for 30 s.
Passing product_image on an avatar video raises the per-second rate by $0.01 on Standard, $0.013 on Plus and $0.03 on Max, which adds $0.30, $0.39 and $0.90 to a 30-second setup-guide intro. The same clip costs $5.82, $7.74 and $17.40 with the image.
Rates are from Sume's public catalog, and the field behaviour is in the avatar video guide, both read 2026-10-04. Omit product_image for a productless video.
Rates side by side
| Tier | No product | With product | Added per second |
|---|---|---|---|
| Standard | $0.184 | $0.194 | $0.01 |
| Plus | $0.245 | $0.258 | $0.013 |
| Max | $0.55 | $0.58 | $0.03 |
A 30-second setup-guide intro
| Item | Standard | Plus | Max |
|---|---|---|---|
| No product image | $5.52 | $7.35 | $16.50 |
| With product image | $5.82 | $7.74 | $17.40 |
| Added by the image | $0.30 | $0.39 | $0.90 |
The request
product_image must be a fetchable public HTTPS image URL. Localhost, private-network, non-HTTPS and non-image responses are rejected before provider submission.
curl -X POST https://api.sume.com/v1/avatar-1.0/talking-video \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: setup-intro-001" \
-d '{"avatar_handle": "docs_host", "aspect_ratio": "16:9", "quality": "plus", "product_image": "https://example.com/inputs/device.png", "scene": {"type": "prompt", "prompt": "Clean desk, soft daylight"}, "script": "Welcome. In the next few steps you will plug in the device, connect it to your network, and name it in the app."}'When the image is worth it
For a setup guide the viewer needs to see which object is meant, so the extra cents are small next to the cost of a confused customer. For a talking-head message with no product, leave the field out.
Sources
Related posts
More in Sume Avatar 1.0
- Split a 3-minute script into 60-second avatar jobs
Sume avatar talking videos accept scripts of an estimated 4-60 seconds. Split a 3-minute script into jobs of that size, then join the audio with timeline audio.
- Ten UGC-style openers, one script: a hook test for $9.20 on Pro
Ten 5-second standard avatar openers cost $9.20 at $0.184 per second, and ten fit inside a Pro queue's first wave of 15. Then you finish only the winner.
- Udemy promo video at 90 s: an avatar intro in two clips
Udemy's guidance puts an ideal promo video near 90 seconds. A Sume avatar clip tops out at 60 seconds, so build the intro as two clips and join them.
- Alt text for an avatar video poster: WCAG 1.1.1 in practice
A poster image from a Sume avatar preview still needs a text alternative under WCAG 1.1.1, and the video needs descriptive identification. What to write.
Written by Sume